anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
Files
9f00a37437ef2dece095b8bd0b3fb5b64f28b59a
vllm-omni/docs/api/README.md
T

116 lines
6.2 KiB
Markdown
Raw Normal View History

[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
# Summary
[Misc] Fix docs and update image edit example with cache-dit (#318)
2025-12-15 21:43:28 +08:00
## Entry Points
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
[Misc] Fix docs and update image edit example with cache-dit (#318)
2025-12-15 21:43:28 +08:00
Main entry points for vLLM-Omni inference and serving.
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
[Feat] Rename AsyncOmniLLM -> AsyncOmni (#103)
2025-11-30 22:26:33 +08:00
- [vllm_omni.entrypoints.async_omni.AsyncOmni][]
[Feature]Basic version of supporting streaming output (#367)
2025-12-31 22:02:04 +08:00
- [vllm_omni.entrypoints.async_omni_diffusion.AsyncOmniDiffusion][]
[Core] Supports stage abstraction in the diffusion model (#391)
2025-12-26 20:59:33 +08:00
- [vllm_omni.entrypoints.async_omni_llm.AsyncOmniLLM][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.entrypoints.chat_utils.OmniAsyncMultiModalContentParser][]
- [vllm_omni.entrypoints.chat_utils.OmniAsyncMultiModalItemTracker][]
- [vllm_omni.entrypoints.chat_utils.parse_chat_messages_futures][]
[Doc]Fix - Align with repo. (#1176)
2026-02-03 18:11:50 +08:00
- [vllm_omni.entrypoints.cli.benchmark.base.OmniBenchmarkSubcommandBase][]
- [vllm_omni.entrypoints.cli.benchmark.main.OmniBenchmarkSubcommand][]
- [vllm_omni.entrypoints.cli.benchmark.serve.OmniBenchmarkServingSubcommand][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.entrypoints.cli.serve.OmniServeCommand][]
[Feature] Support output modalities control per request (#298)
2025-12-17 17:19:56 +08:00
- [vllm_omni.entrypoints.client_request_state.ClientRequestState][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.entrypoints.log_utils.OrchestratorMetrics][]
[Feature]Basic version of supporting streaming output (#367)
2025-12-31 22:02:04 +08:00
- [vllm_omni.entrypoints.log_utils.StageRequestMetrics][]
- [vllm_omni.entrypoints.log_utils.StageStats][]
[diffusion] add doc and fix qwen-image (#96)
2025-11-28 18:07:44 +08:00
- [vllm_omni.entrypoints.omni.Omni][]
[Feature]Basic version of supporting streaming output (#367)
2025-12-31 22:02:04 +08:00
- [vllm_omni.entrypoints.omni.OmniBase][]
[Misc] Fix docs and update image edit example with cache-dit (#318)
2025-12-15 21:43:28 +08:00
- [vllm_omni.entrypoints.omni_diffusion.OmniDiffusion][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.entrypoints.omni_llm.OmniLLM][]
- [vllm_omni.entrypoints.omni_stage.OmniStage][]
[Feature]Basic version of supporting streaming output (#367)
2025-12-31 22:02:04 +08:00
- [vllm_omni.entrypoints.stage_utils.OmniStageTaskType][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
## Inputs
Input data structures for multi-modal inputs.
[Doc]Fix - Align with repo. (#1176)
2026-02-03 18:11:50 +08:00
- [vllm_omni.inputs.data.OmniDiffusionSamplingParams][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.inputs.data.OmniEmbedsPrompt][]
[Doc]Fix - Align with repo. (#1176)
2026-02-03 18:11:50 +08:00
- [vllm_omni.inputs.data.OmniTextPrompt][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.inputs.data.OmniTokenInputs][]
- [vllm_omni.inputs.data.OmniTokensPrompt][]
- [vllm_omni.inputs.parse.parse_singleton_prompt_omni][]
- [vllm_omni.inputs.preprocess.OmniInputPreprocessor][]
## Engine
Engine classes for offline and online inference.
[diffusion] add doc and fix qwen-image (#96)
2025-11-28 18:07:44 +08:00
- [vllm_omni.diffusion.diffusion_engine.DiffusionEngine][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.engine.AdditionalInformationEntry][]
- [vllm_omni.engine.AdditionalInformationPayload][]
[Bugfix] Remove mandatory flash-attn dependency and optimzie docs (#113)
2025-11-30 18:20:44 +08:00
- [vllm_omni.engine.OmniEngineCoreOutput][]
- [vllm_omni.engine.OmniEngineCoreOutputs][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.engine.OmniEngineCoreRequest][]
- [vllm_omni.engine.PromptEmbedsPayload][]
- [vllm_omni.engine.arg_utils.AsyncOmniEngineArgs][]
- [vllm_omni.engine.arg_utils.OmniEngineArgs][]
[Doc] Refine the document. (#403)
2025-12-22 21:29:40 +08:00
- [vllm_omni.engine.input_processor.OmniInputProcessor][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.engine.output_processor.MultimodalOutputProcessor][]
- [vllm_omni.engine.output_processor.OmniRequestState][]
## Core
Core scheduling and caching components.
[Feature]Support async computation and communication across stages by chunks (#727)
2026-01-26 11:21:24 +08:00
- [vllm_omni.core.sched.omni_ar_scheduler.KVCacheTransferData][]
[Bugfix] Fix ci bug for qwen2.5-omni (#230)
2025-12-08 02:43:48 +08:00
- [vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler][]
- [vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler][]
[Feature]Support async computation and communication across stages by chunks (#727)
2026-01-26 11:21:24 +08:00
- [vllm_omni.core.sched.output.OmniCachedRequestData][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.core.sched.output.OmniNewRequestData][]
[Doc]Fix - Align with repo. (#1176)
2026-02-03 18:11:50 +08:00
- [vllm_omni.core.sched.output.OmniSchedulerOutput][]
[Model] Support Qwen3-TTS model series (#895)
2026-01-22 16:57:37 +08:00
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.vq.core_vq.DistributedGroupResidualVectorQuantization][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.vq.core_vq.DistributedResidualVectorQuantization][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.vq.core_vq.EuclideanCodebook][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.vq.core_vq.VectorQuantization][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.vq.core_vq.preprocess][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
[Misc] Fix docs and update image edit example with cache-dit (#318)
2025-12-15 21:43:28 +08:00
## Configuration
Configuration classes.
- [vllm_omni.config.model.OmniModelConfig][]
- [vllm_omni.diffusion.cache.teacache.config.TeaCacheConfig][]
- [vllm_omni.distributed.omni_connectors.utils.config.ConnectorSpec][]
- [vllm_omni.distributed.omni_connectors.utils.config.OmniTransferConfig][]
[Model] Support Qwen3-TTS model series (#895)
2026-01-22 16:57:37 +08:00
- [vllm_omni.model_executor.models.qwen3_tts.configuration_qwen3_tts.Qwen3TTSConfig][]
- [vllm_omni.model_executor.models.qwen3_tts.configuration_qwen3_tts.Qwen3TTSSpeakerEncoderConfig][]
- [vllm_omni.model_executor.models.qwen3_tts.configuration_qwen3_tts.Qwen3TTSTalkerCodePredictorConfig][]
- [vllm_omni.model_executor.models.qwen3_tts.configuration_qwen3_tts.Qwen3TTSTalkerConfig][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_12hz.configuration_qwen3_tts_tokenizer_v2.Qwen3TTSTokenizerV2Config][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_12hz.configuration_qwen3_tts_tokenizer_v2.Qwen3TTSTokenizerV2DecoderConfig][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.configuration_qwen3_tts_tokenizer_v1.Qwen3TTSTokenizerV1Config][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.configuration_qwen3_tts_tokenizer_v1.Qwen3TTSTokenizerV1DecoderBigVGANConfig][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.configuration_qwen3_tts_tokenizer_v1.Qwen3TTSTokenizerV1DecoderConfig][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.configuration_qwen3_tts_tokenizer_v1.Qwen3TTSTokenizerV1DecoderDiTConfig][]
- [vllm_omni.model_executor.models.qwen3_tts.tokenizer_25hz.configuration_qwen3_tts_tokenizer_v1.Qwen3TTSTokenizerV1EncoderConfig][]
[Misc] Fix docs and update image edit example with cache-dit (#318)
2025-12-15 21:43:28 +08:00
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
## Workers
Worker classes and model runners for distributed inference.
[Doc]Fix - Align with repo. (#1176)
2026-02-03 18:11:50 +08:00
- [vllm_omni.diffusion.worker.diffusion_model_runner.DiffusionModelRunner][]
- [vllm_omni.diffusion.worker.diffusion_worker.DiffusionWorker][]
- [vllm_omni.diffusion.worker.diffusion_worker.WorkerProc][]
- [vllm_omni.platforms.npu.worker.npu_ar_model_runner.ExecuteModelState][]
- [vllm_omni.platforms.npu.worker.npu_ar_model_runner.NPUARModelRunner][]
- [vllm_omni.platforms.npu.worker.npu_ar_worker.NPUARWorker][]
- [vllm_omni.platforms.npu.worker.npu_generation_model_runner.NPUGenerationModelRunner][]
- [vllm_omni.platforms.npu.worker.npu_generation_worker.NPUGenerationWorker][]
- [vllm_omni.platforms.npu.worker.npu_model_runner.OmniNPUModelRunner][]
- [vllm_omni.platforms.xpu.worker.xpu_ar_model_runner.XPUARModelRunner][]
- [vllm_omni.platforms.xpu.worker.xpu_ar_worker.XPUARWorker][]
- [vllm_omni.platforms.xpu.worker.xpu_generation_model_runner.XPUGenerationModelRunner][]
- [vllm_omni.platforms.xpu.worker.xpu_generation_worker.XPUGenerationWorker][]
[Doc] Refine the document. (#403)
2025-12-22 21:29:40 +08:00
- [vllm_omni.worker.gpu_ar_model_runner.ExecuteModelState][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.worker.gpu_ar_model_runner.GPUARModelRunner][]
- [vllm_omni.worker.gpu_ar_worker.GPUARWorker][]
[Bugfix] Remove mandatory flash-attn dependency and optimzie docs (#113)
2025-11-30 18:20:44 +08:00
- [vllm_omni.worker.gpu_generation_model_runner.GPUGenerationModelRunner][]
- [vllm_omni.worker.gpu_generation_worker.GPUGenerationWorker][]
[Docs] optimize and supplement docs system (#86)
2025-11-28 11:03:52 +08:00
- [vllm_omni.worker.gpu_model_runner.OmniGPUModelRunner][]
[Doc]Fix - Align with repo. (#1176)
2026-02-03 18:11:50 +08:00
- [vllm_omni.worker.mixins.OmniWorkerMixin][]
Reference in new issue Copy Permalink